[gcc r13-1836] aarch64: Lower vcombine to GIMPLE

[gcc r13-1836] aarch64: Lower vcombine to GIMPLE

[Andrew Carlotti]

https://gcc.gnu.org/g:8a1e05b7618fed394b0928bec89e71748295d357

commit r13-1836-g8a1e05b7618fed394b0928bec89e71748295d357
Author: Andrew Carlotti <andrew.carlotti@arm.com>
Date:   Thu Jul 21 17:07:23 2022 +0100

    aarch64: Lower vcombine to GIMPLE
    
    This lowers vcombine intrinsics to a GIMPLE vector constructor, which enables
    better optimisation during GIMPLE passes.
    
    gcc/
    
            * config/aarch64/aarch64-builtins.cc
            (aarch64_general_gimple_fold_builtin): Add combine.
    
    gcc/testsuite/
    
            * gcc.target/aarch64/advsimd-intrinsics/combine.c:
            New test.

Diff:
---
 gcc/config/aarch64/aarch64-builtins.cc             | 22 ++++++++++++++++++++++
 .../aarch64/advsimd-intrinsics/combine.c           | 18 ++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 2cacb4df8a6..e2a9faa179c 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -2808,6 +2808,28 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt,
 	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
 	break;
 
+     BUILTIN_VDC (BINOP, combine, 0, AUTO_FP)
+     BUILTIN_VD_I (BINOPU, combine, 0, NONE)
+     BUILTIN_VDC_P (BINOPP, combine, 0, NONE)
+	{
+	  tree first_part, second_part;
+	  if (BYTES_BIG_ENDIAN)
+	    {
+	      second_part = args[0];
+	      first_part = args[1];
+	    }
+	  else
+	    {
+	      first_part = args[0];
+	      second_part = args[1];
+	    }
+	  tree ret_type = gimple_call_return_type (stmt);
+	  tree ctor = build_constructor_va (ret_type, 2, NULL_TREE, first_part,
+					    NULL_TREE, second_part);
+	  new_stmt = gimple_build_assign (gimple_call_lhs (stmt), ctor);
+	}
+	break;
+
      /*lower store and load neon builtins to gimple.  */
      BUILTIN_VALL_F16 (LOAD1, ld1, 0, LOAD)
      BUILTIN_VDQ_I (LOAD1_U, ld1, 0, LOAD)
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/combine.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/combine.c
new file mode 100644
index 00000000000..d08faf7a4a1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/combine.c
@@ -0,0 +1,18 @@
+/* { dg-do compile { target { aarch64*-*-* } } } */
+/* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+/*
+** foo:
+**	umov	w0, v1\.s\[1\]
+**	ret
+*/
+
+int32_t foo (int32x2_t a, int32x2_t b)
+{
+  int32x4_t c = vcombine_s32(a, b);
+  return vgetq_lane_s32(c, 3);
+}
+